Mind the Trade-off: Debiasing NLU Models without Degrading the
In-distribution Performance
- URL: http://arxiv.org/abs/2005.00315v1
- Date: Fri, 1 May 2020 11:22:55 GMT
- Title: Mind the Trade-off: Debiasing NLU Models without Degrading the
In-distribution Performance
- Authors: Prasetya Ajie Utama, Nafise Sadat Moosavi, Iryna Gurevych
- Abstract summary: We introduce a novel debiasing method called confidence regularization.
It discourages models from exploiting biases while enabling them to receive enough incentive to learn from all the training examples.
We evaluate our method on three NLU tasks and show that, in contrast to its predecessors, it improves the performance on out-of-distribution datasets.
- Score: 70.31427277842239
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Models for natural language understanding (NLU) tasks often rely on the
idiosyncratic biases of the dataset, which make them brittle against test cases
outside the training distribution. Recently, several proposed debiasing methods
are shown to be very effective in improving out-of-distribution performance.
However, their improvements come at the expense of performance drop when models
are evaluated on the in-distribution data, which contain examples with higher
diversity. This seemingly inevitable trade-off may not tell us much about the
changes in the reasoning and understanding capabilities of the resulting models
on broader types of examples beyond the small subset represented in the
out-of-distribution data. In this paper, we address this trade-off by
introducing a novel debiasing method, called confidence regularization, which
discourage models from exploiting biases while enabling them to receive enough
incentive to learn from all the training examples. We evaluate our method on
three NLU tasks and show that, in contrast to its predecessors, it improves the
performance on out-of-distribution datasets (e.g., 7pp gain on HANS dataset)
while maintaining the original in-distribution accuracy.
Related papers
- Improving Bias Mitigation through Bias Experts in Natural Language
Understanding [10.363406065066538]
We propose a new debiasing framework that introduces binary classifiers between the auxiliary model and the main model.
Our proposed strategy improves the bias identification ability of the auxiliary model.
arXiv Detail & Related papers (2023-12-06T16:15:00Z) - Debiasing Multimodal Models via Causal Information Minimization [65.23982806840182]
We study bias arising from confounders in a causal graph for multimodal data.
Robust predictive features contain diverse information that helps a model generalize to out-of-distribution data.
We use these features as confounder representations and use them via methods motivated by causal theory to remove bias from models.
arXiv Detail & Related papers (2023-11-28T16:46:14Z) - Guide the Learner: Controlling Product of Experts Debiasing Method Based
on Token Attribution Similarities [17.082695183953486]
A popular workaround is to train a robust model by re-weighting training examples based on a secondary biased model.
Here, the underlying assumption is that the biased model resorts to shortcut features.
We introduce a fine-tuning strategy that incorporates the similarity between the main and biased model attribution scores in a Product of Experts loss function.
arXiv Detail & Related papers (2023-02-06T15:21:41Z) - Feature-Level Debiased Natural Language Understanding [86.8751772146264]
Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets.
We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias.
DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
arXiv Detail & Related papers (2022-12-11T06:16:14Z) - Empirical Study on Optimizer Selection for Out-of-Distribution
Generalization [16.386766049451317]
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution.
In this study, we examine the performance of popular first-order generalizations for different classes of distributional shift.
arXiv Detail & Related papers (2022-11-15T23:56:30Z) - Agree to Disagree: Diversity through Disagreement for Better
Transferability [54.308327969778155]
We propose D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data.
We show how D-BAT naturally emerges from the notion of generalized discrepancy.
arXiv Detail & Related papers (2022-02-09T12:03:02Z) - General Greedy De-bias Learning [163.65789778416172]
We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space.
GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
arXiv Detail & Related papers (2021-12-20T14:47:32Z) - End-to-End Self-Debiasing Framework for Robust NLU Training [8.344476599818826]
We introduce a simple yet effective debiasing framework whereby the shallow representations of the main model are used to derive a bias model.
We demonstrate on three well studied NLU tasks that despite its simplicity, our method leads to competitive OOD results.
arXiv Detail & Related papers (2021-09-05T13:20:31Z) - Towards Debiasing NLU Models from Unknown Biases [70.31427277842239]
NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task.
We present a self-debiasing framework that prevents models from mainly utilizing biases without knowing them in advance.
arXiv Detail & Related papers (2020-09-25T15:49:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.